6 papers · 1 filter
Universal Algorithm-Implicit Learning
Stefano Woerner, Seong Joon Oh, Christian F. Baumgartner
Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability. Moreover, the current meta-learning literatu…
Dynamics Reveals Structure: Challenging the Linear Propagation Assumption
Hoyeon Chang, Bálint Mucsányi, Seong Joon Oh
Neural networks adapt through first-order parameter updates, yet it remains unclear whether such updates preserve logical coherence. We investigate the geometric limits of the Line…
LLM generation novelty through the lens of semantic similarity
Philipp Davydov, Ameya Prabhu, Matthias Bethge +2
Generation novelty is a key indicator of an LLM's ability to generalize, yet measuring it against full pretraining corpora is computationally challenging. Existing evaluations ofte…
DISCO: Diversifying Sample Condensation for Efficient Model Evaluation
Alexander Rubinstein, Benjamin Raible, Martin Gubri +1
Evaluating modern machine learning models has become prohibitively expensive. Benchmarks such as LMMs-Eval and HELM demand thousands of GPU hours per model. Costly evaluation reduc…
Scalable Ensemble Diversification for OOD Generalization and Detection
Alexander Rubinstein, Luca Scimeca, Damien Teney +1
Training a diverse ensemble of models has several practical applications such as providing candidates for model selection with better out-of-distribution (OOD) generalization, and…
Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents
Evgenii Kortukov, Alexander Rubinstein, Elisa Nguyen +1
Retrieval-augmented generation (RAG) mitigates many problems of fully parametric language models, such as temporal degradation, hallucinations, and lack of grounding. In RAG, the m…